CN110196896A - A kind of intelligence questions generation method towards the study of external Chinese characters spoken language - Google Patents
A kind of intelligence questions generation method towards the study of external Chinese characters spoken language Download PDFInfo
- Publication number
- CN110196896A CN110196896A CN201910434762.5A CN201910434762A CN110196896A CN 110196896 A CN110196896 A CN 110196896A CN 201910434762 A CN201910434762 A CN 201910434762A CN 110196896 A CN110196896 A CN 110196896A
- Authority
- CN
- China
- Prior art keywords
- question
- answer
- knowledge mapping
- intelligence
- model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/332—Query formulation
- G06F16/3329—Natural language query formulation or dialogue systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses it is a kind of towards external Chinese characters spoken language study intelligence questions generation method, comprising: obtain question and answer to corpus to, building knowledge mapping, Construct question generate model and building intelligence questions generate system application；If obtaining question and answer corpus specifically by drying method；A healthy and strong knowledge mapping frame is constructed, forms triple to fill knowledge mapping to relationship is extracted in corpus from question and answer；Using existing question and answer to and knowledge mapping to the problem of developing generate model be trained；The keyword of user's input is made inferences, is associated and completion, model is generated using problem and generates and meet the question sentence of demand.The present invention is based on the potential relationships that the intelligence questions generation method of knowledge mapping has sufficiently excavated semantic net, improve the efficiency and intelligence of problem generation.
Description
Technical field
The present invention relates to intelligence questions to generate field, asks more particularly to a kind of intelligence towards the study of external Chinese characters spoken language
Inscribe generation method.
Background technique
With the promotion of Chinese international status and influence power, the Chinese as economy and culture carrier has obtained more and more
Attention, the number of countries in the world learning Chinese is also being increasing.Chinese studying can not only promote communication exchange, can also make outer
Compatriots are better understood by the thick and heavy geography carried under language and lexical system, history, cultural connotation, reinforce them to China
The acceptance of culture.
Spoken language is the important component of language learning, is application of the language in actually contacts, it often contains
Deep cultural values.The best mode of Oral Training is dialogue, with speech recognition in artificial intelligence, speech synthesis,
The technologies such as natural language processing are gradually matured, and all kinds of early education robots have become burning hot market product, but are directed to language
Teach by precept learn this vertical field product it is also fewer.Question and answer robot on the market is based on passively answering at present, and imparts knowledge to students
It generally requires actively to teach, therefore problem generation technique is particularly important.According to having the documents chapter data such as textbook, in conjunction with user
The keyword of input makes inferences, and generates question sentence, is the prerequisite ability of language teaching machine people.
Summary of the invention
The present invention is less for Oral Training platform in Chinese teaching, question and answer robot initiative is low and is directed to language-specific
The problems such as robot missing imparted knowledge to students, a kind of intelligent generation problem generation method of combination knowledge mapping is proposed, by obtaining
It takes question and answer to generate model and building intelligence questions generation system to corpus, building knowledge mapping, Construct question, has sufficiently excavated language
The potential relationship of justice net, the efficiency and intelligence that Upgrade Problem generates.
The technical solution adopted by the present invention to solve the technical problems is:
A kind of intelligence questions generation method towards the study of external Chinese characters spoken language, comprising the following steps:
S1: question and answer pair are obtained, comprising:
S11: existing question and answer on network are crawled using scrapy frame；
S12: irregularization text data is handled to obtain question and answer pair by natural language processing technique；
S13: human-edited generates question and answer pair；
S2: building knowledge mapping, comprising:
S21: define the Chinese character knowledge mapping G based on semantic net frame, form be<Ei, R, Ej>；
S22: entity, relationship and entity three are extracted from corpus using the Relation extraction method based on interdependent syntactic analysis
Tuple,
It is stored in neo4j chart database, forms Chinese character knowledge mapping；
S3: Construct question generates model, comprising:
S31: by participle, part-of-speech tagging, syntactic analysis, obtaining triple<Ei from S1 and S2, R, Ej>and its matched
Question and answer pair, respectively as encode the and decode material of model；
S32: the dictionary (including Chinese character, letter, punctuation mark) of maintenance one one-hot coding, vector dimension, that is, dictionary
Greatly
Size；
S33: the RNN model of one introducing attention and LSTM mechanism of building；
S4: building intelligence questions generate system application, comprising:
S41: towards exploitation, problem is generated into model use in question and answer library, enriches the data volume in question and answer library.
S42: problem generation models coupling knowledge mapping is applied to question sentence reasoning, inputed to user by user oriented
Possible problem and answer out.
By the above-mentioned description of this invention it is found that compared with prior art, the invention has the following beneficial effects:
A kind of intelligence questions generation method towards the study of external Chinese characters spoken language of the present invention can help overseas Chinese studying
Person effectively carries out Chinese characters spoken language study, by the information inquiry of the good Structure of Knowledge Representation of knowledge mapping, high speed and deep layer
The advantages that secondary relation inference, makes inferences, associates and completion, problem is used to generate model in conjunction with the keyword that user inputs
Generate the question sentence for meeting demand, the efficiency and intelligence that Upgrade Problem generates.
Detailed description of the invention
Fig. 1 is the flow diagram of the method for the present invention.
Specific embodiment
Present invention will be further explained below with reference to specific examples.It should be understood that these embodiments are merely to illustrate the present invention
Rather than it limits the scope of the invention.In addition, it should also be understood that, after reading the content taught by the present invention, those skilled in the art
Member can make various changes or modifications the present invention, and such equivalent forms equally fall within the application the appended claims and limited
Range.
A kind of intelligence questions generation method towards the study of external Chinese characters spoken language shown in Figure 1, of the invention, including such as
It is lower rapid:
S1: question and answer pair are obtained；
Specifically, including:
S11: crawling existing nlp Chinese question and answer corpus pair on network using scrapy frame, for basic question and answer；
S12: " Chinese " teaching material data are handled to obtain question and answer pair by natural language processing technique；
S13: the teacher and classmate being had wide experience by school's Chinese education profession, to the question and answer of generation to manually being compiled
Volume, additions and deletions change, and are allowed to more meet Chinese teaching reality.
S2: building knowledge mapping；
Specifically, including:
S21: the Chinese character knowledge mapping G based on semantic net frame is defined, information wherein included is by trinary data group
It is<Ei at, form, R, Ej>；
S22: entity, relationship and entity three are extracted from corpus using the Relation extraction method based on interdependent syntactic analysis
Tuple is stored in neo4j chart database, forms Chinese character knowledge mapping.
S3: Construct question generates model；
Specifically, including:
S31: by participle, part-of-speech tagging, syntactic analysis, obtaining triple<Ei from S1 and S2, R, Ej>and its matched
Question and answer pair, respectively as encode the and decode material of model；
S32: the dictionary (including Chinese character, letter, punctuation mark) of maintenance one one-hot coding, vector dimension, that is, dictionary
Size；
S33: the RNN model of one introducing attention and LSTM mechanism of building.
S4: building intelligence questions generate system application；
Specifically, including:
S41: towards exploitation, problem is generated into model use in question and answer library, enriches the data volume in question and answer library.
S42: problem generation models coupling knowledge mapping is applied to question sentence reasoning, inputed to user by user oriented
Possible problem and answer out.
The above is only a specific embodiment of the present invention, but the design concept of the present invention is not limited to this, all to utilize this
Design makes a non-material change to the present invention, and should all belong to behavior that violates the scope of protection of the present invention.
Claims (1)
1. a kind of intelligence questions generation method towards the study of external Chinese characters spoken language, which comprises the following steps:
S1: question and answer pair are obtained, comprising:
S11: existing question and answer on network are crawled using scrapy frame；
S12: irregularization text data is handled to obtain question and answer pair by natural language processing technique；
S13: human-edited generates question and answer pair；
S2: building knowledge mapping, comprising:
S21: define the Chinese character knowledge mapping G based on semantic net frame, form be<Ei, R, Ej>；
S22: entity, relationship and entity ternary are extracted from corpus using the Relation extraction method based on interdependent syntactic analysis
Group,
It is stored in neo4j chart database, forms Chinese character knowledge mapping；
S3: Construct question generates model, comprising:
S31: by participle, part-of-speech tagging, syntactic analysis, triple<Ei, R, Ej>and its matched question and answer are obtained from S1 and S2
It is right, respectively as encode the and decode material of model；
S32: the dictionary of maintenance one one-hot coding, vector dimension, that is, dictionary size；
S33: the RNN model of one introducing attention and LSTM mechanism of building；
S4: building intelligence questions generate system application, comprising:
S41: towards exploitation, problem is generated into model use in question and answer library, enriches the data volume in question and answer library.
S42: problem generation models coupling knowledge mapping is applied to question sentence reasoning by user oriented, and providing to the input of user can
The problem of energy and answer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910434762.5A CN110196896A (en) | 2019-05-23 | 2019-05-23 | A kind of intelligence questions generation method towards the study of external Chinese characters spoken language |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910434762.5A CN110196896A (en) | 2019-05-23 | 2019-05-23 | A kind of intelligence questions generation method towards the study of external Chinese characters spoken language |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110196896A true CN110196896A (en) | 2019-09-03 |
Family
ID=67753044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910434762.5A Pending CN110196896A (en) | 2019-05-23 | 2019-05-23 | A kind of intelligence questions generation method towards the study of external Chinese characters spoken language |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110196896A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111061851A (en) * | 2019-12-12 | 2020-04-24 | 中国科学院自动化研究所 | Given fact-based question generation method and system |
| CN111104517A (en) * | 2019-10-01 | 2020-05-05 | 浙江工商大学 | Chinese problem generation method based on two triplets |
| CN111797244A (en) * | 2020-07-20 | 2020-10-20 | 华侨大学 | Intelligent situation teaching method and system based on knowledge graph and conversation robot |
| CN112380836A (en) * | 2020-11-12 | 2021-02-19 | 华侨大学 | Intelligent Chinese message question generating method |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170330087A1 (en) * | 2016-05-11 | 2017-11-16 | International Business Machines Corporation | Automated Distractor Generation by Identifying Relationships Between Reference Keywords and Concepts |
| CN108681544A (en) * | 2018-03-07 | 2018-10-19 | 中山大学 | A kind of deep learning method described based on collection of illustrative plates topological structure and entity text |
| CN109033277A (en) * | 2018-07-10 | 2018-12-18 | 广州极天信息技术股份有限公司 | Class brain system, method, equipment and storage medium based on machine learning |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
-
2019
- 2019-05-23 CN CN201910434762.5A patent/CN110196896A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170330087A1 (en) * | 2016-05-11 | 2017-11-16 | International Business Machines Corporation | Automated Distractor Generation by Identifying Relationships Between Reference Keywords and Concepts |
| CN108681544A (en) * | 2018-03-07 | 2018-10-19 | 中山大学 | A kind of deep learning method described based on collection of illustrative plates topological structure and entity text |
| CN109062939A (en) * | 2018-06-20 | 2018-12-21 | 广东外语外贸大学 | A kind of intelligence towards Chinese international education leads method |
| CN109033277A (en) * | 2018-07-10 | 2018-12-18 | 广州极天信息技术股份有限公司 | Class brain system, method, equipment and storage medium based on machine learning |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111104517A (en) * | 2019-10-01 | 2020-05-05 | 浙江工商大学 | Chinese problem generation method based on two triplets |
| CN111061851A (en) * | 2019-12-12 | 2020-04-24 | 中国科学院自动化研究所 | Given fact-based question generation method and system |
| CN111061851B (en) * | 2019-12-12 | 2023-08-08 | 中国科学院自动化研究所 | Question generation method and system based on given facts |
| CN111797244A (en) * | 2020-07-20 | 2020-10-20 | 华侨大学 | Intelligent situation teaching method and system based on knowledge graph and conversation robot |
| CN111797244B (en) * | 2020-07-20 | 2022-06-07 | 华侨大学 | Intelligent situation teaching method and system based on knowledge graph and conversation robot |
| CN112380836A (en) * | 2020-11-12 | 2021-02-19 | 华侨大学 | Intelligent Chinese message question generating method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110196896A (en) | A kind of intelligence questions generation method towards the study of external Chinese characters spoken language | |
| CN109902298B (en) | Domain knowledge modeling and knowledge level estimation method in self-adaptive learning system | |
| CN108363743B (en) | Intelligent problem generation method and device and computer readable storage medium | |
| CN110083690A (en) | A kind of external Chinese characters spoken language training method and system based on intelligent answer | |
| CN108829678A (en) | Name entity recognition method in a kind of Chinese international education field | |
| CN108009285A (en) | Forest Ecology man-machine interaction method based on natural language processing | |
| EP4116859A3 (en) | Document processing method and apparatus and medium | |
| Popescu | Linguistic competence vs. Translation competence: A pedagogic approach | |
| Olney | Using novices to scale up intelligent tutoring systems | |
| Pavlic et al. | Adjective representation with the method Nodes of Knowledge | |
| Xiaohong et al. | The application of artificial intelligence in modern foreign language learning | |
| Li | [Retracted] An English Writing Grammar Error Correction Technology Based on Similarity Algorithm | |
| Aoyon et al. | A self-learning French language learner assistant chatbot leveraging deep learning | |
| CN112115722A (en) | Human brain-simulated Chinese analysis method and intelligent interaction system | |
| Riegel et al. | What Does it Take to be Bilingual or Bidialectal. | |
| CN111797244B (en) | Intelligent situation teaching method and system based on knowledge graph and conversation robot | |
| Almuayqil et al. | Towards an ontology-based fully integrated system for student e-assessment | |
| CN112800174A (en) | Insurance automatic question-answering method and system based on knowledge graph | |
| Bednarik et al. | Automated EA-type question generation from annotated texts | |
| Zhao et al. | Design of english writing system based on machine learning | |
| Sun et al. | Research on grammar checking system using computer big data and convolutional neural network constructing classification model | |
| Bakhromkhodja | The Role of Artificial Intelligence in Learning Foreign Languages | |
| Wang et al. | Research on Intelligent Voice Question Answering System for Simulation Training of Thermal Power Plant | |
| Liu et al. | A TMFV-Based Adaptive E-Learning System for Generating and Allocating Questions | |
| Zhang et al. | Exploring Teaching Strategies Integrating University English with Bioinformatics Through Graph Structure Analysis. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190903 |
|
| RJ01 | Rejection of invention patent application after publication |